Journal of Software Engineering Research and Development

Table 20 Chi-squared test for outlier detection applied on maintenance study

From: Model-based reuse for crosscutting frameworks: assessing reuse and maintenance effort

Study	T.	G.	X²	p	Position	Outlier
First	C	1	2.350449	0.1252469	lowest	182.751342
	C	2	2.152789	0.1423112	highest	458.576312
	M	1	5.788559	0.0161308	highest	1952.875079
	M	2	3.598538	0.05783041	highest	1283.533192
Replication	C	1	1.771974	0.183138	highest	1082.486509
	C	2	4.338041	0.03726978	highest	493.115942
	M	1	2.422232	0.1196244	highest	837.879299
	M	2	4.87366	0.02726961	lowest	1554.176697

Chi-squared test is a statistical test used to detect outliers. It was employed to detect eight outliers in the maintenance study. These outliers are removed in the last t-test.

Back to article page